Composition models of distributional semantics are used to construct phrase representations from the representations of their words. Composition models are typically situated on two ends of a spectrum. They either have a small number of parameters but compose all phrases in the same way, or they perform word-specific compositions at the cost of a far larger number of parameters. In this paper we propose transformation weighting (TransWeight), a composition model that consistently outperforms existing models on nominal compounds, adjective-noun phrases, and adverb-adjective phrases in English, German, and Dutch. TransWeight drastically reduces the number of parameters needed compared with the best model in the literature by composing similar words in the same way.

In this paper we analyze the performance of different composition models on a large dataset of German compound nouns.Given a vector space model for the German language, we try to reconstruct the observed representation (the corpusestimated vector) of a compound by composing the observed representations of its two immediate constituents.We explore the composition models proposed in the literature and also present a new, simple model that achieves the best performance on our dataset.

Linguists have domain specific diagrams for syntactic structures, as well as expectations about the "look and feel" of the diagrams. However, these diagrams have received relatively little attention in the information visualization field. In this paper we present two approaches to applying InfoVis techniques to these diagrams to make them interactive and effective in a computer-driven research environment. Results from each approach will influence the further development of the other.